CSEIT1952136 | Received : 01 May 2019 | Accepted : 17 May 2019 | May-June -2019 [ 5 (3) : 127-133 ]
International Journal of Scientific Research in Computer Science, Engineering and Information Technology
© 2019 IJSRCSEIT | Volume 5 | Issue 3 | ISSN : 2456-3307
DOI : 10.32628/CSEIT1952136
127
Social Marketplace Monitoring and Sentiment Analysis
P. Monisha
1
, R. Rubanya
1
, N. Malarvizhi
2
1
BE Scholar, Department of Computer Science and Engineering, IFET College Of Engineering,
Villupuram, India
2
Assistant Professor, Department of Computer Science and Engineering, IFET College of Engineering,
Villupuram, India
ABSTRACT
The overwhelming majority of existing approaches to opinion feature extraction trust mining patterns for one
review corpus, ignoring the nontrivial disparities in word spacing characteristics of opinion options across
completely different corpora. During this research a unique technique to spot opinion options from on-line
reviews by exploiting the distinction in opinion feature statistics across two corpora, one domain-specific
corpus (i.e., the given review corpus) and one domain-independent corpus (i.e., the contrasting corpus). The
tendency to capture this inequality called domain relevance (DR), characterizes the relevancy of a term to a
text assortment. The tendency to extract an inventory of candidate opinion options from the domain review
corpus by shaping a group of grammar dependence rules. for every extracted candidate feature, to have a
tendency to estimate its intrinsic-domain relevancy (IDR) and extrinsic-domain relevance(EDR) scores on the
domain-dependent and domain-independent corpora, severally. Natural language processing (NLP) refers to
computer systems that analyze, attempt understand, or produce one or more human languages, such as English,
Japanese, Italian, or Russian. Process information contained in natural language text. The input might be text,
spoken language, or keyboard input. The field of NLP is primarily concerned with getting computers to
perform useful and interesting tasks with human languages. The field of NLP is secondarily concerned with
helping us come to a better understanding of human language. [23]
Keywords : Intrinsic-Domain Relevancy, Extrinsic-Domain Relevance, Natural Language Processing,
Domain Relevance
I. INTRODUCTION
Opinion mining (also referred to as sentiment
analysis) aims to investigate people’s opinions,
sentiments, and attitudes toward entities like
merchandise, services, and their attributes
[1].Sentiments or opinions expressed in matter
reviews area unit usually analyzed at varied
resolutions. for instance, document-level opinion
mining identifies the general judgment or sentiment
expressed on associate entity(e.g., mobile phone or
hotel) in a very review document, however it doesn't
associate opinions with specific aspects (e.g., display,
battery) of the entity. This drawback conjointly
happens, the' to a lesser extent, in sentence-level
opinion mining, In opinion mining, associate opinion
feature, or feature briefly, indicates associate entity or
associate attribute of associate entity on that users
specific their opinions. during this paper, we tend to
propose a unique approach to the identification of
such options from unstructured matter reviews.